ClawHub
Back to skill

Security audit

Format Tool

Security checks for vulnerabilities and agentic risk

Overview

This is a local text-formatting utility with some documentation mismatch, but no evidence of harmful access, persistence, or hidden behavior.

This skill appears safe to install for simple local text transformations, but users should be aware that its documentation is imprecise: it may offer commands like reverse, sort, unique, and remove-whitespace, while the advertised JSON/CSV/table formatting features are not implemented in the inspected script.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Tp4

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding

The code is generally text-processing related, but the declared description is narrower: it emphasizes beautifying output, cleaning structured data, and aligning columns for readability. The implementation includes several transformations that are not well represented by that description, especially reversing text, sorting lines, deduplicating lines, and stripping all whitespace. These are substantive additional capabilities beyond simple formatting/beautification. There are no concerning permissions or external resource accesses, but the declared purpose does not accurately capture the full behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.